Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.7212. Min Act: -0.1700
Data Index: 523089 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.6587. Min Act: -0.1700
Data Index: 4227666 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5650. Min Act: -0.1700
Data Index: 2485423 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5650. Min Act: -0.1700
Data Index: 1153499 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5650. Min Act: -0.1700
Data Index: 8214363 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5650. Min Act: -0.1700
Data Index: 6361150 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5337. Min Act: -0.1700
Data Index: 2194919 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5025. Min Act: -0.1700
Data Index: 1659236 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4712. Min Act: -0.1700
Data Index: 1062581 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4712. Min Act: -0.1700
Data Index: 1019499 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4712. Min Act: -0.1700
Data Index: 5587331 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.5025. Min Act: -0.1700
Data Index: 566683 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4712. Min Act: -0.1700
Data Index: 7043313 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4712. Min Act: -0.1700
Data Index: 2204660 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4400. Min Act: -0.1700
Data Index: 4525521 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4400. Min Act: -0.1700
Data Index: 2810961 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4400. Min Act: -0.1700
Data Index: 4298555 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4400. Min Act: -0.1700
Data Index: 3639900 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4087. Min Act: -0.1700
Data Index: 3357208 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7212. Min Range: -6.7212
Max Act: 6.4087. Min Act: -0.1700
Data Index: 5452482 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19